record_lesson · Lessons MCP: Risk & Policy

WHAT IT DOES

What record_lesson does on Lessons

AI agents use record_lesson to create or update resources in Lessons — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lessons environment.

WHY IT NEEDS A POLICY

Why record_lesson needs a policy

The tool writes a new lesson entry to the store. While it checks for duplicates before inserting, its primary action is creating/storing new data, which is reversible (the record can be deleted). No code execution, financial transactions, or irreversible destruction is implied.

From the tool's definition 'Record a new lesson learned' — creates new data; 'Checks for duplicates' implies insertion logic with deduplication, not a read-only operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

record_lesson Rate-limited

record_lesson stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "record_lesson": {
      "limits": [
        {
          "counter": "record_lesson_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Lessons, so you can run agents against it safely.

FAQ

Questions about record_lesson

What does the record_lesson tool do? +

Record a new lesson learned. Checks for duplicates by comparing. It is categorised as a Write tool in the Lessons MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on record_lesson? +

Register the Lessons MCP server in PolicyLayer and add a rule for record_lesson: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Lessons. Nothing to install.

What risk level is record_lesson? +

record_lesson is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit record_lesson? +

Yes. Add a rate_limit block to the record_lesson rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block record_lesson completely? +

Set action: deny in the PolicyLayer policy for record_lesson. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides record_lesson? +

record_lesson is provided by the Lessons MCP server (sosoyososo/lesson-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.